Summary:
Favor the extended reg patterns over the shifted reg patterns that match
only the operand shift and not the full sign/zero extend and shift.
Reviewers: jmolloy, t.p.northover
Subscribers: mcrosier, aemerson, llvm-commits, rengolin
Differential Revision: http://reviews.llvm.org/D11569
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243753 91177308-0d34-0410-b5e6-96231b3b80d8
It's potentially more efficient on Cyclone, and from the optimization guides &
schedulers looks like it has no effect on Cortex-A53 or A57. In general you'd
expect a MOV to be about the most efficient instruction with its semantics,
even though the official "UXTW" alias is really a UBFX.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243576 91177308-0d34-0410-b5e6-96231b3b80d8
This commit defines subtarget feature strict-align and uses it instead of
cl::opt -aarch64-strict-align to decide whether strict alignment should be
forced.
rdar://problem/21529937
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243516 91177308-0d34-0410-b5e6-96231b3b80d8
The 'common' section TLS is not implemented.
Current C/C++ TLS variables are not placed in common section.
DWARF debug info to get the address of TLS variables is not generated yet.
clang and driver changes in http://reviews.llvm.org/D10524
Added -femulated-tls flag to select the emulated TLS model,
which will be used for old targets like Android that do not
support ELF TLS models.
Added TargetLowering::LowerToTLSEmulatedModel as a target-independent
function to convert a SDNode of TLS variable address to a function call
to __emutls_get_address.
Added into lib/Target/*/*ISelLowering.cpp to call LowerToTLSEmulatedModel
for TLSModel::Emulated. Although all targets supporting ELF TLS models are
enhanced, emulated TLS model has been tested only for Android ELF targets.
Modified AsmPrinter.cpp to print the emutls_v.* and emutls_t.* variables for
emulated TLS variables.
Modified DwarfCompileUnit.cpp to skip some DIE for emulated TLS variabls.
TODO: Add proper DIE for emulated TLS variables.
Added new unit tests with emulated TLS.
Differential Revision: http://reviews.llvm.org/D10522
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243438 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
Add patterns for doing floating point round with various rounding modes
followed by conversion to int as a single FCVT* instruction.
Reviewers: t.p.northover, jmolloy
Subscribers: aemerson, rengolin, mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D11424
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243422 91177308-0d34-0410-b5e6-96231b3b80d8
This path add the aarch64 lowering of __builtin_thread_pointer. It uses
the already implemented AArch64ISD::THREAD_POINTER used in TLS generation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243412 91177308-0d34-0410-b5e6-96231b3b80d8
be reserved.
The decision to reserve x18 is going to be made solely by the front-end,
so it isn't necessary to check if the OS is Darwin in the backend.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243308 91177308-0d34-0410-b5e6-96231b3b80d8
When truncating to non-legal types (such as i16, i8 and i1) always use an AND
instruction to mask out the upper bits. This was only done when the source type
was an i64, but not when the source type was an i32.
This commit fixes this and adds the missing i32 truncate tests.
This fixes rdar://problem/21990703.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243198 91177308-0d34-0410-b5e6-96231b3b80d8
whether register x18 should be reserved.
This change is needed because we cannot use a backend option to set
cl::opt "aarch64-reserve-x18" when doing LTO.
Out-of-tree projects currently using cl::opt option "-aarch64-reserve-x18"
to reserve x18 should make changes to add subtarget feature "reserve-x18"
to the IR.
rdar://problem/21529937
Differential Revision: http://reviews.llvm.org/D11463
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243186 91177308-0d34-0410-b5e6-96231b3b80d8
Before creating a schedule edge to encourage MacroOpFusion check that:
- The predecessor actually writes a register that the branch reads.
- The predecessor has no successors in the ScheduleDAG so we can
schedule it in front of the branch.
This avoids skewing the scheduling heuristic in cases where macroop
fusion cannot happen.
Differential Revision: http://reviews.llvm.org/D10745
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242723 91177308-0d34-0410-b5e6-96231b3b80d8
The idea of deferred spilling is to delay the insertion of spill code until the
very end of the allocation. A "candidate" to spill variable might not required
to be spilled because of other evictions that happened after this decision was
taken. The spirit is similar to the optimistic coloring strategy implemented in
Preston and Briggs graph coloring algorithm.
For now, this feature is highly experimental. Although correct, it would require
much more modification to properly model the effect of spilling.
Anyway, this early patch helps prototyping this feature.
Note: The test case cannot unfortunately be reduced and is probably fragile.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242585 91177308-0d34-0410-b5e6-96231b3b80d8
C11 leaves the choice on whether round-to-integer operations set the inexact
flag implementation-defined. Darwin does expect it to be set, but this seems to
be against the intent of the IEEE document and slower to implement anyway. So
it should be opt-in.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242446 91177308-0d34-0410-b5e6-96231b3b80d8
This is a new iteration of the reverted r238793 /
http://reviews.llvm.org/D8232 which wrongly assumed that any and/or
trees can be represented by conditional compare sequences, however there
are some restrictions to that. This version fixes this and adds comments
that explain exactly what types of and/or trees can actually be
implemented as conditional compare sequences.
Related to http://llvm.org/PR20927, rdar://18326194
Differential Revision: http://reviews.llvm.org/D10579
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242436 91177308-0d34-0410-b5e6-96231b3b80d8
Current implementation handles unordered comparison poorly in soft-float mode.
Consider (a ULE b) which is a <= b. It is lowered to (ledf2(a, b) <= 0 || unorddf2(a, b) != 0) (in general). We can do better job by lowering it to (__gtdf2(a, b) <= 0).
Such replacement is true for other CMP's (ult, ugt, uge). In general, we just call same function as for ordered case but negate comparison against zero.
Differential Revision: http://reviews.llvm.org/D10804
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242280 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
processFunctionBeforeCalleeSavedScan was renamed to determineCalleeSaves and now takes a BitVector parameter as of rL242165, reviewed in http://reviews.llvm.org/D10909
WebAssembly is still marked as experimental and therefore doesn't build by default. It does, however, grep by default! I notice that processFunctionBeforeCalleeSavedScan is still mentioned in a few comments and error messages, which I also fixed.
Reviewers: qcolombet, sunfish
Subscribers: jfb, dsanders, hfinkel, MatzeB, llvm-commits
Differential Revision: http://reviews.llvm.org/D11199
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242242 91177308-0d34-0410-b5e6-96231b3b80d8
Fixes PR23804: assertion failure in emitPrologue in the case of a
function with an empty frame and a dynamic alloca that needs stack
realignment. This is a typical case for AddressSanitizer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241943 91177308-0d34-0410-b5e6-96231b3b80d8
If our two inputs have known top-zero bit counts M and N, we trivially
know that the output cannot have any bits set in the top (min(M, N)-1)
bits, since nothing could carry past that point.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241927 91177308-0d34-0410-b5e6-96231b3b80d8
Tim Northover has told me that they can occur when the compiler cleverly
constructs constants - as demonstrated in the test case.
rdar://21703486
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241641 91177308-0d34-0410-b5e6-96231b3b80d8
Since the NvCast is generated by the selection process the concerns about
endianess and bit reversal don't apply.
rdar://21703486
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241611 91177308-0d34-0410-b5e6-96231b3b80d8
The assertion in getCopyFromPartsVector assumed that the vector 'part' must
match the type of argument (arguments are potentially split into multiple
parts). However, in some cases the targets return a 'part' of the right size
but with a different type. We already handle this case correctly later on
and generate a bitcast. This commit just makes sure that we are actually
checking the property that we care about.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241312 91177308-0d34-0410-b5e6-96231b3b80d8
The personality routine currently lives in the LandingPadInst.
This isn't desirable because:
- All LandingPadInsts in the same function must have the same
personality routine. This means that each LandingPadInst beyond the
first has an operand which produces no additional information.
- There is ongoing work to introduce EH IR constructs other than
LandingPadInst. Moving the personality routine off of any one
particular Instruction and onto the parent function seems a lot better
than have N different places a personality function can sneak onto an
exceptional function.
Differential Revision: http://reviews.llvm.org/D10429
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239940 91177308-0d34-0410-b5e6-96231b3b80d8
It's been used before to avoid infinite loops caused by separate CGP
optimizations undoing one another. We found one more such issue
caused by r238054. To avoid it, generalize the "InsertedTruncs"
set to any inst, and use it to avoid touching those again.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239938 91177308-0d34-0410-b5e6-96231b3b80d8
The patch triggers a miscompile on SPEC 2006 403.gcc with the (ref)
200.i and scilab.i inputs. I opened PR23866 to track analysis of this.
This reverts commit r238793.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239880 91177308-0d34-0410-b5e6-96231b3b80d8
These are really immediate DUPs, and suffer from the same problem
with long instructions with a high/2 variant (e.g. smull).
By extending a MOVI (or DUP, before this patch), we can avoid an ext
on the other operand of the long instruction, e.g. turning:
ext.16b v0, v0, v0, #8
movi.4h v1, #0x53
smull.4s v0, v0, v1
into:
movi.8h v1, #0x53
smull2.4s v0, v0, v1
While there, add a now-necessary combine to fold (VT NVCAST (VT x)).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239799 91177308-0d34-0410-b5e6-96231b3b80d8
LLVM targeting aarch64 doesn't correctly produce aligned accesses for non-aligned
data at -O0/fast-isel (-mno-unaligned-access).
The root cause seems to be in fast-isel not producing unaligned access correctly
for -mno-unaligned-access.
The patch just aborts fast-isel for loads and stores when -mno-unaligned-access is
present.
The regression test is updated to check this new test case (-mno-unaligned-access
together with fast-isel).
Differential Revision: http://reviews.llvm.org/D10360
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239732 91177308-0d34-0410-b5e6-96231b3b80d8
Re-commit after adding "-aarch64-neon-syntax=generic" to fix the failure on OS X.
This patch was firstly committed in r239514, then reverted in r239544 because of a syntax incompatible failure on OS X.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239711 91177308-0d34-0410-b5e6-96231b3b80d8
Revert "[AArch64] Match interleaved memory accesses into ldN/stN instructions."
Revert "Fixing MSVC 2013 build error."
The test/CodeGen/AArch64/aarch64-interleaved-accesses.ll test was failing on OS X.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239544 91177308-0d34-0410-b5e6-96231b3b80d8
Store instructions do not modify register values and therefore it's safe
to form a store pair even if the source register has been read in between
the two store instructions.
Previously, the read of w1 (see below) prevented the formation of a stp.
str w0, [x2]
ldr w8, [x2, #8]
add w0, w8, w1
str w1, [x2, #4]
ret
We now generate the following code.
stp w0, w1, [x2]
ldr w8, [x2, #8]
add w0, w8, w1
ret
All correctness tests with -Ofast on A57 with Spec200x and EEMBC pass.
Performance results for SPEC2K were within noise.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239432 91177308-0d34-0410-b5e6-96231b3b80d8
Now that we can look at users, we can trivially do this: when we would
have otherwise disabled GlobalMerge (currently -O<3), we can just run
it for minsize functions, as it's usually a codesize win.
Differential Revision: http://reviews.llvm.org/D10054
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239087 91177308-0d34-0410-b5e6-96231b3b80d8
If the compare in a select pattern has another use then it can't be removed, so we'd just
be creating repeated code if we created a min/max node.
Spotted by Matt Arsenault!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239037 91177308-0d34-0410-b5e6-96231b3b80d8
Previously CCMP/FCCMP instructions were only used by the
AArch64ConditionalCompares pass for control flow. This patch uses them
for SELECT like instructions as well by matching patterns in ISelLowering.
PR20927, rdar://18326194
Differential Revision: http://reviews.llvm.org/D8232
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@238793 91177308-0d34-0410-b5e6-96231b3b80d8
Geoff Berry
Tim Northover
Akira Hatanaka
Chih-Hung Hsieh
Adhemerval Zanella
Juergen Ributzka
Weiming Zhao
Matthias Braun
Chad Rosier
Quentin Colombet
John Brawn
Alexey Bataev
JF Bastien
Evgeniy Stepanov
Fiona Glaser
Arnaud A. de Grandmaison
Renato Golin
Arnold Schwaighofer
Nadav Rotem
Hao Liu
Eric Christopher
Yi Jiang
David Majnemer
Ahmed Bougacha
Evgeny Astigeevich
Rafael Espindola
James Molloy